Platform reliability · ENSEK energy SaaS
Here's what AI can do for this role — and what still needs a human. Built straight from ENSEK's own job advert, running live on my_db.ensek_demo.infra_metrics — 5,000 real rows via MotherDuck (DuckDB). Not a slide about AI. The job, getting done.
Every line on the left is lifted from ENSEK's actual job ad. If a card lacks a harvested JD line, it is omitted. On the right is the AI doing it — with eligible cards running live against the warehouse and offline inspection clearly labelled in the workspace.
“Implementing best practices for monitoring, alerting, and incident response using DataDog and other tools.”
What is average CPU utilisation and p99 latency across services — which services are the most resource-intensive?
bar chart“Designing, building, and maintaining cost-effective, reliable, and scalable AWS infrastructure.”
What is the error rate per service — which services are generating the most errors relative to request volume?
kpi“Collaborating with cross-functional teams to identify and address performance bottlenecks and reliability issues.”
Which days had the highest error volumes — is there a pattern in when errors spike?
deviation“Conducting post-incident reviews to analyse root causes and implement preventive measures.”
Which services are under the highest memory and disk I/O pressure — where are the non-CPU resource risks?
bar chart“Automating routine tasks and processes to improve efficiency.”
How does daily request volume and error rate trend across the week — is traffic growing and are errors correlated?
bar chart“Implementing best practices for monitoring, alerting, and incident response using DataDog and other tools.”
What is the combined SRE health scorecard — CPU, memory, latency and error rate in one view?
tableThe honest other half. AI does the analysis; a person owns the decision — especially where regulation, fairness and accountability bite.
A plain-English question — the same one the job ad describes — is translated to SQL by the agentic backend.
Curated cards run server-side against MotherDuck when eligible. The workspace separately labels any local inspection path.
Runs against my_db.ensek_demo.infra_metrics (5,000 rows declared by the manifest). No synthetic numbers.
Each figure carries a falsifier — recomputed from the result set, not a stored number, so it can't quietly drift.
It's the role getting done: curated questions run live server-side against the warehouse; local inspection is labelled inside the workspace.
Open the live workspace →Provenance. Live ENSEK microservice telemetry: 5,000 rows, five services (api-gateway, auth-svc, billing-svc, customer-portal, data-pipeline), hourly metrics 2025-06-01 to 2025-06-07. Schema: my_db.ensek_demo.infra_metrics. Local fallback uses the same pre-projected slice in-browser.
It's Sorted — I took ENSEK's job ads and didn't write a report on what AI could do. I built it. Get the rest sorted →
I'm trained on this proof and the real ENSEK: the Ignition meter-to-cash platform (seven modules), the move under Centrica in 2024, 7M+ energy accounts migrated for suppliers like British Gas and Utility Warehouse, and the Ofgem framing. Ask me how the Data Analyst function changes shape, or which open roles map to which Ignition module.